Applications of AI-Driven Practice in Road Freight Transport Decarbonisation: A Quantitative Systematic Literature Review

This paper systematically reviews the applications of artificial intelligence (AI)-driven practices in road freight transport (RFT) decarbonisation. RFT scenarios are becoming increasingly complex, and the deep decarbonisation challenge is still severe. AI-driven practices are regarded as a transformative frontier and a key path to addressing them. However, related research is mainly confined to a single disciplinary background, which may hinder the field from making substantial progress in designing diverse solutions and exploring collaborative decarbonisation mechanisms in multiple transportation stages. This review conducts bibliometric analysis and science mapping on 227 articles, following the SPAR-4-SLR protocol. The performance analysis reveals exponential growth in publications over the past decade, especially in the past 3 years. Bibliographic coupling identifies eight knowledge clusters including powertrain energy management, strategic fleet electrification, intermodal corridor planning, and physics-informed co-optimisation, collectively evidencing a field-wide transition from isolated vehicle-level efficiency gains toward system-integrated decarbonisation architectures. Cross-cluster analysis exposes structural integration gaps at the boundaries of mature clusters, from which stage-specific future research opportunities are proposed across different RFT phases. The findings argue that consequential advances will arise from coupling AI-driven demand forecasting, powertrain control, and emission accounting into end-to-end collaborative optimisation frameworks, rather than from continued single-technology refinement.